# Google mcp-toolbox.

Every CVE that names Google mcp-toolbox among its affected products, newest first. Vendors and products are as the CNA wrote them.

## Records, newest first

- [Authentication Bypass and Audience Confusion in MCP Toolbox OAuth Provider](https://agentprime.io/advisories/CVE-2026-14541.md)
  `CVE-2026-14541` · CVE record: Google mcp-toolbox · CVSS 8.0 High · Not analysed yet · Published 31 Jul 2026 · Tags: Authentication bypass
- [Server-Side Request Forgery via Unrestricted HTTP Redirection in MCP Toolbox](https://agentprime.io/advisories/CVE-2026-14540.md)
  `CVE-2026-14540` · CVE record: Google mcp-toolbox · CVSS 8.0 High · Not analysed yet · Published 31 Jul 2026 · Tags: Server-side request forgery (SSRF)
- [Denial of Service via Unrestricted Payload Buffering in MCP Toolbox](https://agentprime.io/advisories/CVE-2026-14539.md)
  `CVE-2026-14539` · CVE record: Google mcp-toolbox · CVSS 6.6 Medium · Not analysed yet · Published 31 Jul 2026 · Tags: Denial of service
- [BigQuery Dataset Allowlist Bypass via Metadata Dry-Run in MCP Toolbox](https://agentprime.io/advisories/CVE-2026-14538.md)
  `CVE-2026-14538` · CVE record: Google mcp-toolbox · CVSS 5.7 Medium · Not analysed yet · Published 31 Jul 2026 · Tags: Broken access control
- [Authorization Bypass in MCP Toolbox Legacy HTTP Endpoints](https://agentprime.io/advisories/CVE-2026-14537.md)
  `CVE-2026-14537` · CVE record: Google mcp-toolbox · CVSS 8.1 High · Not analysed yet · Published 31 Jul 2026 · Tags: Broken access control

## Filters and formats

Filters are query parameters on this URL: `q` (words, as in a web search engine: `"a phrase"`, `OR`, `-word`; an id; a package or product name), `severity` (low, medium, high or critical), `critical=1`, `kev=1`, `ecosystem` (npm, pypi, packagist, go, maven, rubygems, crates, nuget, hex), `kind=package`, `assigner` (a CNA’s short name), `min_score` and `state`. Each record’s title links to its Markdown page.

- The same list as JSON: <https://api.agentprime.io/v1/advisories?technology=google-mcp-toolbox>
- Every list: <https://agentprime.io/advisories.md>, critical: <https://agentprime.io/advisories/critical.md>; by weakness: <https://agentprime.io/advisories/tag/sql-injection.md> and the other tags in <https://agentprime.io/llms.txt>; by technology: `/advisories/technology/<slug>.md` (`fortinet-fortimail`)

---

The web page: <https://agentprime.io/advisories/technology/google-mcp-toolbox/>. Everything for agents: <https://agentprime.io/llms.txt>.